{"id":"https://openalex.org/W2607593044","doi":"https://doi.org/10.18653/v1/p17-2058","title":"Differentiable Scheduled Sampling for Credit Assignment","display_name":"Differentiable Scheduled Sampling for Credit Assignment","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2607593044","doi":"https://doi.org/10.18653/v1/p17-2058","mag":"2607593044"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2058","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2058","pdf_url":"https://www.aclweb.org/anthology/P17-2058.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2058.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112236395","display_name":"Kartik Goyal","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kartik Goyal","raw_affiliation_strings":["Carnegie Mellon University Pittsbrugh, PA, USA","Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsbrugh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111222692","display_name":"Chris Dyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Chris Dyer","raw_affiliation_strings":["DeepMind London, UK","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind London, UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh, PA, USA","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7945822477340698},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7220721244812012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6526695489883423},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6325699090957642},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5890825986862183},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5871025323867798},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5526221990585327},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4587230384349823},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.4568234086036682},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42001521587371826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3587542176246643},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33900249004364014},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.23578926920890808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22249451279640198}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7945822477340698},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7220721244812012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6526695489883423},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6325699090957642},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5890825986862183},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5871025323867798},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5526221990585327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4587230384349823},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.4568234086036682},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42001521587371826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587542176246643},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33900249004364014},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.23578926920890808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22249451279640198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p17-2058","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2058","pdf_url":"https://www.aclweb.org/anthology/P17-2058.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.06970","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.06970","pdf_url":"https://arxiv.org/pdf/1704.06970","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2607593044","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.06970.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1704.06970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.06970","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-2058","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2058","pdf_url":"https://www.aclweb.org/anthology/P17-2058.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2607593044.pdf","grobid_xml":"https://content.openalex.org/works/W2607593044.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W889023230","https://openalex.org/W1843891098","https://openalex.org/W2010624529","https://openalex.org/W2311132329","https://openalex.org/W2414484917","https://openalex.org/W2487501366","https://openalex.org/W2547875792","https://openalex.org/W2578492184","https://openalex.org/W2949185007","https://openalex.org/W2949888546","https://openalex.org/W2950178297","https://openalex.org/W2950304420","https://openalex.org/W2950513854","https://openalex.org/W2951777936","https://openalex.org/W2962957031","https://openalex.org/W2963248296","https://openalex.org/W2964308564","https://openalex.org/W3041866211"],"related_works":["https://openalex.org/W2964308564","https://openalex.org/W2130942839","https://openalex.org/W2963403868","https://openalex.org/W3105997200","https://openalex.org/W3141609478","https://openalex.org/W2581730455","https://openalex.org/W2952573015","https://openalex.org/W3027290317","https://openalex.org/W2471458901","https://openalex.org/W2948320335","https://openalex.org/W3048688049","https://openalex.org/W3180887884","https://openalex.org/W2951243569","https://openalex.org/W2875787325","https://openalex.org/W2949675925","https://openalex.org/W1964406070","https://openalex.org/W2114820562","https://openalex.org/W3118969969","https://openalex.org/W3013722860","https://openalex.org/W2766302638"],"abstract_inverted_index":{"We":[0],"demonstrate":[1,43],"that":[2,53],"a":[3,15,39,44],"continuous":[4],"relaxation":[5],"of":[6],"the":[7,30],"argmax":[8],"operation":[9],"can":[10],"be":[11],"used":[12],"to":[13,18,47],"create":[14],"differentiable":[16],"approximation":[17,28],"greedy":[19],"decoding":[20],"for":[21],"sequence-tosequence":[22],"(seq2seq)":[23],"models.":[24],"By":[25],"incorporating":[26],"this":[27],"into":[29],"scheduled":[31,60],"sampling":[32,61],"training":[33,58],"procedure":[34],"In":[35],"addition,":[36],"by":[37],"using":[38],"related":[40],"approximation,":[41],"we":[42,51],"similar":[45],"approach":[46,55],"sampled-based":[48],"training.":[49],"Finally,":[50],"show":[52],"our":[54],"outperforms":[56],"cross-entropy":[57],"and":[59,71],"procedures":[62],"in":[63],"two":[64],"sequence":[65],"prediction":[66],"tasks:":[67],"named":[68],"entity":[69],"recognition":[70],"machine":[72],"translation.":[73]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}